Franziska Mueller is a Research Scientist at Google Zurich , specializing in Augmented Perception . Prior to joining Google, she earned her Ph.D. in Computer Science at Saarland University under the supervision of Prof. Dr. Christian Theobalt, focusing on real-time hand reconstruction from RGB and depth images. Ph.D. in Computer Science (2016-2020) at Saarland University Master’s and Bachelor’s in Computer Science at Saarland University Research visits at Stanford University (2018) and Reality Labs Research (2019) Her research emphasizes the integration of model-based techniques and machine learning components for real-time 3D hand pose estimation, occlusion handling, and hand-object interaction tracking. Key contributions include methods for single-camera reconstruction and datasets like HandSeg. Scientific Awards : Dr. Eduard Martin Award (2021) Google PhD Fellowship (2017) Günter-Hotz-Medal (2016) Bachelor Award (2015) Völklinger Abiturpreis (2012)
Georg Martius is a Full Professor in the Department of Computer Science at the University of Tübingen's Faculty of Science and a Max Planck Research Group Leader at the MPI for Intelligent Systems. Since April 2023, he has been a core member of the DFG-funded Cluster of Excellence 'Machine Learning: New Perspectives for Science,' which received extended funding through 2032 for its mission to integrate machine learning into fundamental scientific discovery processes. His academic foundation includes a PhD from the University of Göttingen and Bernstein Center for Computational Neuroscience (2005), a Diploma in Computer Science from the University of Leipzig (2003), and a visiting research period at the University of Edinburgh's Division of Informatics. Postdoctoral positions followed at the Max Planck Institutes for Dynamics and Self-Organization (Göttingen, 2009), Mathematics in the Sciences (Leipzig, 2010), and IST Austria (2015). Professor Martius's research pioneers the intersection of reinforcement learning, robotics, and tactile sensing, with emphasis on developing autonomous systems capable of natural locomotion, dexterous manipulation, and physical-world understanding. His work bridges theoretical machine learning with practical hardware applications, particularly in creating differentiable simulators, superresolution tactile sensors, and biologically plausible learning frameworks for robotic control. Analysis of his 2024-2025 publications reveals dominant trends in offline reinforcement learning (especially goal-conditioned and diversity-maximization techniques), object-centric representation learning for video understanding, and tactile sensing innovations. A strong thread connects foundation models to world model construction, while his work on differentiable physics engines enables precise collision handling and contact dynamics for real-world robotic control. His leadership roles include directing the Distributed Intelligence research team at Tübingen and contributing to major collaborative initiatives like the Real Robot Challenge and Myochallenge 2022. The Cluster of Excellence appointment represents recognition of his contributions to transforming scientific methodology through machine learning, particularly in automating hypothesis generation and experimental design. Current projects focus on integrating large-scale machine learning with embodied intelligence, advancing tactile perception systems like the Minsight vision-based sensor, and developing neuroplasticity-inspired approaches for robust out-of-distribution detection. His work directly impacts fields requiring physical interaction intelligence, from autonomous navigation to medical robotics, with emphasis on sample-efficient learning from limited real-world data.
Chuang Gan is an Assistant Professor at the University of Massachusetts Amherst, affiliated with the College of Information and Computer Sciences and the Department of Computer Science. His work focuses on advancing artificial intelligence, robotics, computer vision, and embodied agents through interdisciplinary research combining neural networks, physical simulations, and multimodal learning. Research interests include generative models, reinforcement learning, vision-language integration, and scalable autonomous systems. He explores topics like world modeling for robots, adaptive policy learning, and physics-driven AI. His projects often involve creating systems that learn from visual, auditory, and tactile inputs to perform complex tasks such as object manipulation, navigation, and decision-making in dynamic environments. Recent research trends emphasize embodied AI systems capable of long-horizon planning, compositional reasoning, and efficient learning from limited data. His work bridges theory and practice, with applications in robotics, simulation platforms, and multimodal generation. Key contributions include frameworks for 3D scene understanding, adaptive world models, and novel training paradigms for large language models. His research has been applied to robotics platforms like RoboDreamer and UBSoft, focusing on unbounded soft environments. Collaborations involve designing benchmarks for physical scene understanding (e.g., Physion++), and creating tools like DiffTactile for tactile simulation. His work often integrates principles from differential geometry, PDE dynamics, and game theory. Chuang Gan’s research group develops open-source tools and benchmarks, such as the SoftZoo robot co-design platform and the SOK-Bench situated reasoning benchmark. His team emphasizes scalable alignment methods beyond human supervision and explores ethical AI through principles like symmetry-enhanced training.
Adam Finkelstein is a Professor in the Department of Computer Science at Princeton University, where he has been a faculty member since 1997. He holds a PhD and Master's in Computer Science from the University of Washington and a dual degree in Physics and Computer Science from Swarthmore College. Finkelstein is renowned for his interdisciplinary work at the intersection of computer graphics, audio processing, and machine learning, and he co-organized the Art of Science exhibition at Princeton. Education: PhD, Computer Science, University of Washington MS, Computer Science, University of Washington BA, Physics and Computer Science, Swarthmore College His research spans audio processing (e.g., speech enhancement, voice conversion, audio metrics), computer graphics (e.g., line drawing algorithms, stylized rendering, image manipulation), and machine learning (e.g., self-supervised learning, differentiable programming). His work often bridges technical and creative domains, exemplified by collaborations at Pixar and Adobe Creative Technologies Lab. Recent publications highlight advancements in audio super-resolution and voice conversion using deep learning frameworks, as well as stylized line rendering for animated 3D models. His contributions to perceptual audio metrics and shader optimization further underscore his impact on human-centric computational systems. Scientific Awards: NSF CAREER Award Alfred P. Sloan Fellowship Fellow of the Association for Computing Machinery (ACM) Finkelstein has secured foundational grants for his research and actively mentors students, though no specific advisees are listed. He also explores collaborative tools for internet music performance, reflecting his broader interest in distributed systems and user interfaces.
Alexei A. Efros is the Howard Friesen Professor in the EECS Department at UC Berkeley, affiliated with the Berkeley Artificial Intelligence Research (BAIR) Lab. Previously, he spent a decade at CMU's Robotics Institute and held a postdoc at the University of Oxford under Andrew Zisserman. He collaborates with INRIA/École Normale Supérieure in Paris. His research focuses on self-supervised learning, generative models, and visual data mining, with applications to robotics, computational photography, and art. Education & Academic Roles: Postdoc at Oxford (with Andrew Zisserman), faculty at CMU (2005–2015), currently at UC Berkeley. Teaches courses like CS 180/280A (Computer Vision) and CS 280 (Graduate Computer Vision). Research Interests: Self-supervised learning, generative models (e.g., diffusion models, inpainting), visual commonsense, and cross-modal reasoning. His work bridges computer vision and graphics, emphasizing data-driven approaches. Recent projects include Visual Jenga, Diffusion Models as Data Mining Tools, and Prioritized Generative Replay. Grants & Labs: Leads the Efros Research Group, advised over 40 PhD students (e.g., Jun-Yan Zhu, Tinghui Zhou). Collaborates with institutions like INRIA and NVIDIA. Active in grants related to AI, vision, and robotics. Labs/Teams: BAIR Lab (UC Berkeley), former affiliations with CMU Robotics Institute and Willow Team (INRIA/ENS Paris). Current lab focuses on generative AI, 3D perception, and visual reasoning.
Shuran Song is an Assistant Professor of Electrical Engineering at Stanford University, with a courtesy appointment in Computer Science. Previously, she was faculty at Columbia University. She holds a Ph.D. in Computer Science from Princeton University and a BEng from HKUST. Her research focuses on the intersection of computer vision and robotics, particularly in embodied AI, robot manipulation, and sensorimotor learning. Song's work emphasizes learning from physical interactions to enable robots to perform complex tasks autonomously. She leads the Robotics and Embodied AI Lab (REAL@Stanford) and has received prestigious awards, including the NSF Career Award, Sloan Fellowship, and Microsoft Faculty Fellowship. Education: Ph.D., Computer Science, Princeton University; BEng, HKUST Affiliations: Stanford School of Engineering, Department of Electrical Engineering Research interests include deformable object manipulation, visuomotor policy learning, and generalizable robot skills. Her lab develops algorithms for robots to learn through interaction, with applications in household assistance (e.g., TidyBot) and industrial automation. Notable contributions include the TossingBot and Diffusion Policy frameworks. Publications span robotics, computer vision, and AI conferences (RSS, ICRA, CVPR), focusing on policy learning, deformable object handling, and embodied intelligence. Awards highlight her impact in advancing robot learning and perception. Advises doctoral and master's students in robotics and AI, and collaborates on grants from NSF, DoD, and industry partners. Teaches courses on robot perception and embodied AI at Stanford.
Dr. Benjamin Busam is a Senior Research Scientist at the Technical University of Munich , affiliated with the Chair for Computer Science Applications in Medicine under Prof. Nassir Navab. Starting September 2025, he will hold the Professorship for Photogrammetry and Remote Sensing at TUM. His career includes leadership roles at FRAMOS Imaging Systems and Huawei Research in London. Education: Mathematics (TUM), Mathematics and Physics (ParisTech, University of Melbourne), PhD in Mathematics (TUM, 2014) His research focuses on 3D computer vision , multi-modal sensor fusion , and their applications in collaborative robotics and augmented reality . He specializes in projective geometry , 6D pose estimation , and neural radiance fields , with a particular emphasis on photometrically challenging environments. Recent publications highlight advancements in 3D scene understanding , neural rendering , and medical imaging , often leveraging machine learning and vision-language models . His work has been recognized through awards like the EMVA Young Professional Award (2015) and Innovation Pioneer of the Year (2019) , along with multiple Outstanding Reviewer distinctions at leading conferences. Dr. Busam has supervised numerous PhD and MSc students on topics including 6D pose estimation , medical augmented reality , and robotic ultrasound , collaborating with institutions like MIT , École Polytechnique , and University of Padova .
Peter Schroeder is the Shaler Arthur Hanisch Professor of Computer Science and Applied and Computational Mathematics at the California Institute of Technology (Caltech). He holds a B.S. from the Technical University of Berlin (1987), M.S. from MIT (1990), M.A. and Ph.D. from Princeton University (1992–1994). His academic roles at Caltech include Assistant Professor (1995–1998), Associate Professor (1998–2001), Professor (2001–2013), and Hanisch Professor since 2013. He served as Division Deputy Chair (2012–2015) and Acting Director of the Center for Advanced Computing Research (2013–2014). Schroeder’s research focuses on numerical algorithms for computer graphics, geometric modeling, and physical simulation. His work emphasizes Discrete Differential Geometry, rebuilding classical differential geometry for computational applications. Key areas include cloth deformation, fluid dynamics, and vortex simulations. Notable contributions include 'Schrödinger’s smoke' and fluid visualization techniques using Clebsch maps. His publications span ACM Transactions on Graphics and address topics like constrained Willmore surfaces, filament-based plasma models, and shape reconstruction from metrics. He has received the ACM Fellowship and Best Paper in Geometry Processing Award. His research often bridges computational mathematics with artistic and engineering challenges, such as simulating ink chandeliers and solar flares. Schroeder’s academic leadership includes co-founding the ACM SIGGRAPH Academy and mentoring students like James R. McLaughlin and Yanke Song, both recipients of the Henry Ford II Scholar Award.
Wenzel Jakob is an Associate Professor and leader of the Realistic Graphics Lab at EPFL's School of Computer and Communication Sciences , currently on sabbatical at the University of Tokyo until Fall 2025. His work bridges inverse graphics , physically based rendering , and compiler/systems research , with a focus on developing robust differentiable rendering frameworks. Key research themes include: Backpropagation through rendering algorithms for inverse problems Material appearance modeling and optical measurement systems Compiler design for differentiable rendering pipelines Manifold sampling techniques and light transport derivatives His group created Mitsuba renderer , Dr.Jit , and Instant Meshes (recipient of the SGP Software Award). Recent publications (2021–2024) explore volumetric rendering, SDF-based differentiable systems, and efficient Monte Carlo estimators. Awards include the ACM SIGGRAPH Significant Researcher Award , Eurographics Young Researcher Award , and ERC Starting Grant . Teaching roles (2016–2024) span Advanced Computer Graphics and Numerical Methods for Visual Computing courses at EPFL.
Aaron M. Dollar is the Frederick W. Beinecke Professor of Mechanical Engineering at Yale University, affiliated with the Yale Grab Lab. His research focuses on robotics, mechatronics, robotic grasping, and prosthetics, emphasizing adaptive mechanisms and human-robot interaction. He holds a PhD from Harvard University (2008) and degrees from UMass Amherst. Key research areas include dexterous manipulation, underactuated mechanisms, and assistive devices. His work bridges theory and practical applications, with contributions to prosthetic hands, robotic hands, and modular robotics systems. Recipient of prestigious awards: TR35 Innovator (2010), NSF CAREER Award (2010), DARPA Young Faculty Award (2013), and Air Force Young Investigator Award (2011). Developed the Yale MyoAdapt Hand, a single-actuator prosthetic with high functionality. Pioneered methods in real-to-sim transfer, modular lattice printing, and energy-aware robotic exploration. His lab, the Yale Grab Lab, explores robotics, prosthetics, and human motion analysis. Recent projects include autonomous calibration systems (ARC-Calib) and low-cost robotic hardware (RB5 Explorer).
Nicholas Antipa is an Assistant Professor at the University of California San Diego's Jacobs School of Engineering, in the Electrical and Computer Engineering department. His research focuses on the co-design of optical systems and algorithms to develop advanced computational imaging systems, leveraging innovations in 3D printing, sensors, machine learning, and AI. He holds a PhD in Computational Imaging from UC Berkeley and previously worked at the Lawrence Livermore National Lab on optical metrology for the National Ignition Facility. His work includes pioneering projects like the DiffuserCam and Miniscope3D, which enable high-dimensional optical signal capture and 3D microscopy. Education: PhD in Computational Imaging, UC Berkeley (2020) MS in Optics, University of Rochester Institute of Optics BS in Optical Science and Engineering, UC Davis Research Interests: Computational imaging systems, single-shot high-dimensional optical capture, lensless imaging, and applications in neuroscience and marine science. His lab explores novel optical designs, compressed sensing, and AI-driven imaging techniques to push the boundaries of conventional systems. Scientific Awards: Best Paper at ICCP 2019, 2016 Best Demo at ICCP 2017 No. 2 in Optica 15 Top-Cited Articles (2020) Affiliations: Director of the Computational Imaging Systems Lab at UCSD. Collaborates with institutions like Lawrence Livermore National Lab and the Scripps Institution of Oceanography for projects in marine sediment mapping and underwater object detection. His lab emphasizes open-source tools, such as the DiffuserCam Raspberry Pi tutorial.
Jeong Joon (JJ) Park is an Assistant Professor in the Department of Computer Science and Engineering at the University of Michigan. His research focuses on computer vision, graphics, and artificial intelligence with applications in 3D/4D reconstruction, generative modeling, robotics, and medical imaging. He holds a position in the College of Engineering and actively seeks PhD students and postdoctoral researchers aligned with his research interests. Dr. Park’s work emphasizes interdisciplinary approaches, combining geometric deep learning with generative models to address challenges in scene understanding, novel view synthesis, and multi-modal perception. His lab explores both foundational techniques and applied systems, often collaborating with industry and academia on real-world problems. Key research directions include diffusion models for sparse data restoration, trajectory-conditioned 4D generation, and uncertainty-aware sensor fusion for autonomous systems. His publications span top-tier conferences like CVPR, ICCV, and NeurIPS, reflecting a strong publication record in computer vision and graphics. He teaches courses in computer vision and advises students on advanced projects requiring significant weekly commitments. Prospective applicants are encouraged to apply through the U-M CSE PhD program and contact him directly for collaboration opportunities.
Wojciech Jarosz is an Associate Professor of Computer Science at Dartmouth College, affiliated with the College of Engineering and Computer Science. His research focuses on computer graphics, particularly light transport simulation, rendering algorithms, and digital fabrication. He co-founded the Visual Computing Lab and previously led the rendering group at Disney Research Zürich. Jarosz holds a Ph.D. and M.S. from UC San Diego and a B.S. from the University of Illinois Urbana-Champaign. His educational background includes studies in computer science and engineering, with a strong emphasis on graphics and rendering. Research interests span light transport simulation, Monte Carlo methods, appearance capture, and fabrication. Notable achievements include the Eurographics Young Researcher Award (2013) and the NSF CAREER Award (2019). Jarosz's work integrates theoretical rigor with practical applications, such as real-time rendering techniques and volumetric light transport. His lab develops tools for artistic authoring, including intuitive metaphors for volumetric lighting in animated films. Recent projects explore wave-optics BSDF models, optical heterodyne rendering, and unifying radiative transfer models. Key awards include the SIGGRAPH 2024 Best Paper Award and Neukom Institute prizes. His teaching includes courses on rendering algorithms, computer graphics, and computational photography. Jarosz collaborates with industry (e.g., Disney, NVIDIA) and advocates for diversity in computer graphics research.
Ruohan Gao is an Assistant Professor in the Department of Computer Science at the University of Maryland, College Park , with affiliate appointments at the University of Maryland Institute for Advanced Computer Studies (UMIACS) , Maryland Robotics Center (MRC) , and Artificial Intelligence Interdisciplinary Institute at Maryland (AIM) . His research focuses on Computer Vision and Machine Learning , emphasizing Multisensory Machine Intelligence that integrates sight, sound, and touch . He aims to enable machines to perceive, understand, and interact with the world as humans do, with applications in robotic manipulation , audio-visual localization , and differentiable rendering . Article Trends : Span 2018–2025 , centering on audio-visual perception , multisensory datasets , and robotics . Recurring themes include object-centric learning , sound synthesis , and cross-modal consistency . Scientific Awards : Michael H. Granof Award (UT Austin’s Top 1 Doctoral Dissertation, 2021) Best Paper Award Runner-Up (BMVC 2021) Best Paper Award Finalist (CVPR 2019) Highlight Paper (CVPR 2023) He leads the UMD Multisensory Machine Intelligence Lab and collaborates with institutions like Stanford and The University of Texas at Austin . Contact: rhgao@umd.edu .
Yuanbo Xiangli is a postdoctoral researcher at Cornell University , advised by Prof. Noah Snavely. Previously, he obtained his Ph.D. from the Multimedia Lab in the Department of Information Engineering at the Chinese University of Hong Kong (CUHK) , supervised by Prof. Dahua Lin. His research focuses on 3D computer vision and deep generative modeling for urban scene reconstruction. 3D scene reconstruction from sparse images Neural rendering and Gaussian splatting Deep generative modeling for urban environments Multi-source geospatial data processing City-scale modeling and synthetic datasets His recent work includes advanced NeRF extensions (BungeeNeRF, GridNeRF), Gaussian splatting enhancements (GSDF, Scaffold-GS), and urban scene datasets (MatrixCity, OmniCity). A pioneer in combining classical vision techniques with modern deep learning approaches. ICLR 2020 Spotlight Award Collaborates with leading researchers in photorealistic rendering, including Noah Snavely and Dahua Lin. Develops systems enabling efficient 3D reconstruction from diverse data sources like satellite imagery and street-level panoramas.
